metadata
license: cc-by-nc-4.0
base_model: MCG-NJU/videomae-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: videomae-base-finetuned-SLT-subset
results: []
videomae-base-finetuned-SLT-subset
This model is a fine-tuned version of MCG-NJU/videomae-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1513
- Accuracy: 1.0
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- training_steps: 944
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9224 | 0.06 | 59 | 3.7150 | 0.025 |
| 3.9538 | 1.06 | 118 | 3.7131 | 0.025 |
| 3.8824 | 2.06 | 177 | 3.6952 | 0.025 |
| 3.8135 | 3.06 | 236 | 3.6851 | 0.05 |
| 3.8444 | 4.06 | 295 | 3.6689 | 0.025 |
| 3.7715 | 5.06 | 354 | 3.6183 | 0.05 |
| 3.6616 | 6.06 | 413 | 3.4405 | 0.4 |
| 3.6175 | 7.06 | 472 | 3.0778 | 0.325 |
| 3.1062 | 8.06 | 531 | 2.0972 | 0.75 |
| 1.8942 | 9.06 | 590 | 1.2638 | 0.925 |
| 1.3975 | 10.06 | 649 | 0.7811 | 0.975 |
| 1.0269 | 11.06 | 708 | 0.4473 | 1.0 |
| 0.3623 | 12.06 | 767 | 0.3073 | 1.0 |
| 0.3611 | 13.06 | 826 | 0.2007 | 1.0 |
| 0.1881 | 14.06 | 885 | 0.1614 | 1.0 |
| 0.1773 | 15.06 | 944 | 0.1513 | 1.0 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3